comparison queue_genotype_workflow.py @ 4:163ecfba5961 draft

Uploaded

3:36f8098ff528

def get_history_dataset_id_by_name(gi, history_id, dataset_name, outputfh):
    # Use the Galaxy API to get the bcftools merge dataset id
    # from the current history.
    outputfh.write("\nSearching for history dataset named %s.\n" % str(dataset_name))
    history_dataset_dicts = get_history_datasets(gi, history_id)
    for name, hd_dict in history_dataset_dicts.items():
        name = name.lower()
        if name.startswith(dataset_name.lower()):
            outputfh.write("Found dataset named %s.\n" % str(dataset_name))
            return hd_dict['id']
    return None

    # Map the history datasets to the input datasets for the workflow.
    workflow_inputs = {}
    outputfh.write("\nMapping datasets from history to workflow %s.\n" % workflow_name)
    steps_dict = workflow_dict.get('steps', None)
    if steps_dict is not None:
        for step_index, step_dict in steps_dict.items():
            # Dicts that define dataset inputs for a workflow
            # look like this.
            # "0": {
            #      "tool_id": null,
            #      "tool_version": null,

            annotation = step_dict.get('annotation', None)
            if tool_id is None and tool_type == 'data_input' and annotation is not None:
                annotation_check = annotation.lower()
                # inputs is a list and workflow input datasets
                # have no inputs.
                for input_hda_name, input_hda_dict in history_datasets.items():
                    input_hda_name_check = input_hda_name.lower()
                    if input_hda_name_check.find(annotation_check) >= 0:
                        workflow_inputs[step_index] = {'src': 'hda', 'id': input_hda_dict['id']}
                        outputfh.write(" - Mapped dataset %s from history to workflow input dataset with annotation %s.\n" % (input_hda_name, annotation))
                        break

def update_workflow_params(workflow_dict, dbkey, outputfh):
    parameter_updates = None
    name = workflow_dict['name']
    outputfh.write("\nChecking for tool parameter updates for workflow %s using dbkey %s.\n" % (name, dbkey))
    step_dicts = workflow_dict.get('steps', None)
    for step_id, step_dict in step_dicts.items():
        tool_id = step_dict['tool_id']
        if tool_id is None:
            continue
        # Handle reference_source entries
        if tool_id.find('affy2vcf') > 0:

4:163ecfba5961

def get_history_dataset_id_by_name(gi, history_id, dataset_name, outputfh):
    # Use the Galaxy API to get the bcftools merge dataset id
    # from the current history.
    outputfh.write("\nSearching for history dataset named %s.\n" % str(dataset_name))
    history_dataset_dicts = get_history_datasets(gi, history_id)
    for name, hd_dict in list(history_dataset_dicts.items()):
        name = name.lower()
        if name.startswith(dataset_name.lower()):
            outputfh.write("Found dataset named %s.\n" % str(dataset_name))
            return hd_dict['id']
    return None

    # Map the history datasets to the input datasets for the workflow.
    workflow_inputs = {}
    outputfh.write("\nMapping datasets from history to workflow %s.\n" % workflow_name)
    steps_dict = workflow_dict.get('steps', None)
    if steps_dict is not None:
        for step_index, step_dict in list(steps_dict.items()):
            # Dicts that define dataset inputs for a workflow
            # look like this.
            # "0": {
            #      "tool_id": null,
            #      "tool_version": null,

            annotation = step_dict.get('annotation', None)
            if tool_id is None and tool_type == 'data_input' and annotation is not None:
                annotation_check = annotation.lower()
                # inputs is a list and workflow input datasets
                # have no inputs.
                for input_hda_name, input_hda_dict in list(history_datasets.items()):
                    input_hda_name_check = input_hda_name.lower()
                    if input_hda_name_check.find(annotation_check) >= 0:
                        workflow_inputs[step_index] = {'src': 'hda', 'id': input_hda_dict['id']}
                        outputfh.write(" - Mapped dataset %s from history to workflow input dataset with annotation %s.\n" % (input_hda_name, annotation))
                        break

def update_workflow_params(workflow_dict, dbkey, outputfh):
    parameter_updates = None
    name = workflow_dict['name']
    outputfh.write("\nChecking for tool parameter updates for workflow %s using dbkey %s.\n" % (name, dbkey))
    step_dicts = workflow_dict.get('steps', None)
    for step_id, step_dict in list(step_dicts.items()):
        tool_id = step_dict['tool_id']
        if tool_id is None:
            continue
        # Handle reference_source entries
        if tool_id.find('affy2vcf') > 0: